Links to presenters' sides are now included below, where available.
The first day of the conference comprises a range of workshops, to be held on Tuesday 9th December. Delegates will find these events to be especially valuable where there is a current need to consider the introduction of new AI technologies into their own organisations.
There will be four half-day workshops, including the Nineteenth UK CBR Workshop. Delegates are free to choose any combination of morning and afternoon sessions to attend. The programme of workshops is shown below. Note that the morning session starts at 11 a.m. to reduce the need for delegates to stay in Cambridge on the previous night. There is a lunch break from 12.30-13.15 and there are refreshment breaks from 14.45-15.15 and from 16.45-17.00.
Workshops organiser: Professor Adrian Hopgood, Sheffield Hallam University
Stream 1 - Morning (11.00-12.30 and 13.15-14.45 Upper Hall)
AI in Medical Imaging
Co-chairs: Dr Roger Tait and Dr Cinly Ooi, University of Cambridge
Representing a medium for analyses, medical imaging has found roots in many branches of medicine. With growing numbers of imaging modalities being made available to researchers, computational intelligence techniques (such as support vector machines) are an increasingly practical tool in diagnoses and treatment response analyses. Encompassing experts from the diverse and often disconnected fields of computer science and clinical medicine, artificial intelligence in medical imaging is not commonly taught at university level but learnt through on-the-job practical experience. The resultant knowledge transfer barrier stagnates development of the discipline, resulting in lost opportunities for healthcare providers and patients alike.
This workshop is aimed at motivating cross-discipline interaction and discussion, for practitioners of the two distinctly different fields.
Stream 1 - Afternoon (15.15-16.45 and 17.00-18.30 Upper Hall)
AI for Data Mining
Chair: Dr Stephen Matthews, Newcastle University
AI methods for knowledge representation can attempt to model human knowledge with fuzzy sets. For example, we may describe the weather as hot; we may consider two vehicles to have a high degree of similarity; or we may express a preference for an ice cream flavour. This workshop will explain the different interpretations of fuzzy sets and demonstrate how they can be leveraged by different data mining tasks to find patterns in data. Practical examples will be given and real-world applications will be discussed. The aim of the workshop is to provide practical knowledge of applying the discussed methods and to raise awareness of potential pitfalls.
Stream 2 - Morning (11.00-12.30 and 13.15-14.45 Peterhouse Lecture Theatre)
Fundamentals of Hyper-heuristics
Chair: Dr Ender Ozcan, University of Nottingham
Designing an effective and efficient search methodology for computationally difficult real-world problems is often a challenging task. The current state-of-the-art in search methodologies tends to focus on custom-built systems. In general, such systems are expensive to build but provide successful results, since they are specifically tailored for the problem in hand. The experience of an expert plays a major role in the development of a bespoke system but is still often characterised by trial and error. Unfortunately, application of such systems to new problem domains, or sometimes even new problem instances from a known domain, still requires expert involvement in many cases. This is an issue faced by many researchers, along with practitioners, arising mainly from the considerable range of algorithm and/or parameter choices that such systems would require, and the lack of theoretical or practical guidance regarding how to proceed for selecting them.
Hyper-heuristics have emerged as methodologies that can automatically aid the design and implementation of more efficient, effective, reusable, easier-to-implement/deploy/use, adaptive and general computational search methods that are applicable to a range of real-world problems. This tutorial will cover the fundamentals of hyper-heuristics including background, their classification, design options, software tools (focusing on HyFlex v1.0), their application to real-world problems as case studies and recent developments in the area.
Stream 2 - Afternoon (15.15-16.45 and 17.00-18.30 Peterhouse Lecture Theatre)
Nineteenth UK Case-Based Reasoning workshop